Triple
T4617962
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Local Fluff |
E100911
|
entity |
| Predicate | velocityRelativeTo |
P8103
|
FINISHED |
| Object | Sun of several kilometers per second |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Sun of several kilometers per second | Statement: [Local Fluff, velocityRelativeTo, Sun of several kilometers per second]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: velocityRelativeTo Context triple: [Local Fluff, velocityRelativeTo, Sun of several kilometers per second]
-
A.
velocityRelativeToSun
chosen
Indicates the speed and direction of an entity’s motion measured with respect to the Sun as the reference frame.
-
B.
symbolForVelocity
Indicates that one entity is used as the symbolic representation or notation for the concept of velocity of another entity.
-
C.
relativeMotionType
Indicates the type or nature of motion occurring between two entities relative to one another.
-
D.
relativePosition
Indicates the spatial relationship of one entity’s location with respect to another entity’s position.
-
E.
movesRelativeTo
Indicates that one entity changes its position or orientation with respect to another entity, rather than with respect to a fixed reference frame.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69bd43cf363c819087fd5ab441b4a3f4 |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd59e247448190ad92f194cb1127c5 |
completed | March 20, 2026, 2:29 p.m. |
| PD | Predicate disambiguation | batch_69bd522fd5c48190ad2bffc0a5bc9061 |
completed | March 20, 2026, 1:57 p.m. |
Created at: March 20, 2026, 1:12 p.m.